arXiv cs.CL· Zanwu Liu, Dan Zhang, Xiaodi Wang, Yongbo Mao, Xiaoyang Guo, Yonglin Wu, Peiyue Jiang, Yangyang Wei, Zecheng Lin·· 2 天前AI 评分22
MASP：面向主动对话的心理化对抗自博弈框架
Stop Training Against Soft Users: Mentalized Adversarial Self-Play for Proactive Dialogue
AI 导读
MASP 是一个心理化对抗自博弈框架，将主动对话建模为系统与理性抵抗用户之间的部分可观测博弈，用 BDI 潜在状态表示用户演化心理，并分离奖励侧教师心理化与策略侧学生心理化，交替更新系统与用户策略。
正文 · 原文
Abstract:Proactive dialogue agents must guide multi-turn interactions toward task goals while adapting to users whose intentions and attitudes evolve. Existing planners improve system side action selection through search, learned policies, or user aware planning, but are often trained and evaluated against fixed or overly compliant simulators; as a result, high simulated success can reflect soft user bias rather than robust dialogue ability. We introduce MASP, a Mentalized Adversarial Self Play framework that treats proactive dialogue as a partially observable game between a system and a rationally resisting user. MASP represents the user's evolving mental state with a BDI based latent state, separates reward side teacher mentalization from policy side student mentalization, and alternates self play updates for the system and user policies. This turns robustness to rational resistance into a training objective rather than only an evaluation condition. Across diverse proactive dialogue benchmarks, compared with the widely used SFT and Planner-only approaches, MASP substantially improves success rate (SR) and rationality constrained success (RCSR), reduces average turns (AT), and performs better against hard users who make the task goal more difficult to achieve.
| Comments: | Accepted to EMNLP 2026 (Main Conference). 18 pages including references and appendices; 1 figure |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.21156 [cs.CL] |
| (or arXiv:2610.21156v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.21156 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zanwu Liu [view email]
[v1]
Thu, 15 Oct 2026 03:15:40 UTC (241 KB)
来源：arXiv cs.CL · arxiv.org